#TidyTuesday - Week 43
Horror Movies
#define packages desired
dependencies <- c("tidyverse", "plotly", "ggmap", "quantmod", "countrycode", "mgcv", "broom")
#check if pacakges are installed - load if so, install+load if not)
for (i in dependencies) {
if (i %in% row.names(installed.packages())){
eval(bquote(library(.(i))))
message(paste("loaded package",i))
} else {
install.packages(i)
eval(bquote(library(.(i))))
}
}
#This week's data is from the IMDB by way of Kaggle
horror_movies <-
readr::read_csv(
"https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-10-22/horror_movies.csv"
)
#register google api for lat long of filming locations
#register_google(key="<your key here (free @ https://developers.google.com/maps/documentation/maps-static/get-api-key)>", write=T)Use google’s api to gather lat and long of filming locations
Data wringlin’
horror_movies$currency <- gsub("[0-9,[:space:]]", "", horror_movies$budget) #strip currency
horror_movies$currency <- gsub("\\$", "USD", horror_movies$currency) #convert symbols to currency abbrvs
horror_movies$currency <- gsub("\\£", "GBP", horror_movies$currency)
horror_movies$currency <- gsub("\\€", "EUR", horror_movies$currency)
horror_movies$currency <- gsub("RUR", "RUB", horror_movies$currency) #1 RUB == 1000 RUR (Old Russian Ruble obsolete ca. 1998 - from coinmill.com) - change to get updated currency value
horror_movies$currency <- gsub("TRL", "TRY", horror_movies$currency) #1 TRY == 1000000 TRL (Old Turkis Lire obsolete ca. 2005 - from coinmill.com) - change to get updated currency value
horror_movies$currency <- str_remove_all(horror_movies$currency, "\\s") #compulsively remove the spaces
currencies <- unique(horror_movies$currency)[-1]#store uniq currency for conversions
horror_movies$run.time.num <- as.numeric(gsub(" min","", horror_movies$movie_run_time))
#weed out the unrecognized currencies
# for(i in currencies){
# getQuote(paste0(i,"USD","=X"))
# print(i)
# }
xchange.current <- getQuote(paste0(currencies, rep("USD", length(currencies)),"=X")) #get current exchange rate for currencies to USD, can replace USD with desired currency
horror_movies$value.in.usd <- as.numeric(gsub("[^0-9]", "", horror_movies$budget))
#convert budgets to usd
for(i in 1:nrow(horror_movies)){
if(!is.na(horror_movies$value.in.usd[i])){
horror_movies$value.in.usd[i] <- horror_movies$value.in.usd[i]*xchange.current$Last[which(grepl(horror_movies$currency[i], substr(row.names(xchange.current),1,3)))]
}
}
#adjust RUR to RUB
for(i in which(horror_movies$currency=="RUB")){
horror_movies$value.in.usd[i] <- horror_movies$value.in.usd[i]/1000
}
#Adjust TRL to TRY
for(i in which(horror_movies$currency=="TRY")){
horror_movies$value.in.usd[i] <- horror_movies$value.in.usd[i]/1000000
}
#Add region and continent information
horror_movies$region <- countrycode(sourcevar = horror_movies$release_country, origin = "country.name", destination = "region")
horror_movies$continent <- countrycode(sourcevar = horror_movies$release_country, origin = "country.name", destination = "continent")#generate figure
plot_ly(horror_movies,
y=~review_rating,
x=~log(value.in.usd),
color=~continent,
size = ~run.time.num,
text = ~paste0('<b>',title,'</b>', '<br>','<br>',
'Review rating: ', review_rating, '<br>',
'log(Budget) (in $USD): $', value.in.usd, '<br>',
'Run-time: ', movie_run_time, '<br>',
'Language: ', language,'<br>',
'Release Country: ', release_country)) %>%
add_annotations(text = "Conintent Released",
xref = "paper",
yref = "paper",
x = 1.01,
xanchor = "left",
y = .67,
yanchor = "top",
legendtitle = TRUE,
showarrow = FALSE) %>%
layout(title="Log Transformed Budgets vs Reviews",
yaxis = list(title = 'Review Rating'),
xaxis = list(title = 'log(Budget) in $USD', position =0),
legend = list(x=100,y=.5, text='title'),
images = list(
source = "https://media.istockphoto.com/photos/fog-background-picture-id845785528?k=6&m=845785528&s=612x612&w=0&h=VRNazaue6d8xtOBMnV01OV1bpsmo_TfsDVi84gXx278=",
xref = "x",
yref = "y",
x= -10,
y= 10,
sizex = 40,
sizey = 10,
sizing = 'stretch',
opacity = 0.4,
layer='below'
)
)## No trace type specified:
## Based on info supplied, a 'scatter' trace seems appropriate.
## Read more about this trace type -> https://plot.ly/r/reference/#scatter## No scatter mode specifed:
## Setting the mode to markers
## Read more about this attribute -> https://plot.ly/r/reference/#scatter-mode## Warning: Ignoring 2180 observations## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.This figure shows the relationship between budget (log scale, converted to USD) and rating. Each maker is sized by runtime and colored by continental origin.
locations$region <- countrycode(sourcevar = locations$release_country, origin = "country.name", destination = "region")
locations$continent <- countrycode(sourcevar = locations$release_country, origin = "country.name", destination = "continent")
g <- list(
showland = TRUE,
showlakes = TRUE,
showcountries = TRUE,
showocean = TRUE,
countrywidth = 0.5,
x=1,y=1,
landcolor = toRGB("grey50"),
lakecolor = toRGB("grey90"),
oceancolor = toRGB("grey24"),
projection = list(
type = 'orthographic',
rotation = list(
lon = -100,
lat = 40,
roll = 0
)
))
plot_geo(locations, locationmode = 'USA-states', sizes = c(1, 250),
text = ~paste0('<b>',title,'</b>', '<br>','<br>',
'Filimg Location: ', filming_locations, '<br>',
'Review rating: ', review_rating, '<br>',
'Run-time: ', movie_run_time, '<br>',
'Language: ', language,'<br>',
'Release Country: ', release_country)) %>%
add_annotations(text = "Conintent Released",
xref = "paper",
yref = "paper",
x = 1.01,
xanchor = "left",
y = .67,
yanchor = "top",
legendtitle = TRUE,
showarrow = FALSE) %>%
add_markers(
x = ~lon,
y = ~lat,
size = ~review_rating,
color = ~continent) %>%
layout(title = 'The World\'s Spookiest Places (if filming locations are an indicator)', geo = g,
legend = list(x=100,y=.5))## Warning: Ignoring 4 observations## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.This plot displays all filming locations from the provided dataset. Each marker is sized by movie rating and colored by continent of release
#####Bonus I have not gotten to yet
#Using historical exchange rate data from https://fred.stlouisfed.org, gathered by Datopian (https://datahub.io/core)…not today
## Parsed with column specification:
## cols(
## Date = col_date(format = ""),
## Country = col_character(),
## Value = col_double()
## )Determine number of listed cast